insait-institute/bggpt-gemma-2-27b-it-v1.0-gguf v1.0.Q8_0 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
insait-institute/bggpt-gemma-2-27b-it-v1.0-gguf overview
BgGPT-Gemma-2-27B-IT-v1.0-GGUF BgGPT is distributed under Gemma Terms of Use. This repo contains the GGUF format model files for INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0.
Downloads
469
Likes
5
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
9 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| BgGPT-Gemma-2-27B-IT-v1.0.F16-00001-of-00003.gguf | GGUF | F16 | 18.45 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.F16-00002-of-00003.gguf | GGUF | F16 | 18.56 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.F16-00003-of-00003.gguf | GGUF | F16 | 13.71 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q4_K_M.gguf | GGUF | Q4_K_M | 15.50 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q4_K_S.gguf | GGUF | Q4_K_S | 14.66 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q5_K_M.gguf | GGUF | Q5_K_M | 18.08 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q5_K_S.gguf | GGUF | Q5_K_S | 17.59 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q6_K.gguf | GGUF | Q6_K | 20.81 GB | Download |
| BgGPT-Gemma-2-27B-IT-v1.0.Q8_0.gguf | GGUF | — | 26.95 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "gemma",
"frontmatter": {
"license": "gemma"
},
"hero_image_url": "",
"summary": "# BgGPT-Gemma-2-27B-IT-v1.0-GGUF BgGPT is distributed under Gemma Terms of Use. This repo contains the GGUF format model files for INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: gemma\n---\n# BgGPT-Gemma-2-27B-IT-v1.0-GGUF\n\nBgGPT is distributed under [Gemma Terms of Use](https://ai.google.dev/gemma/terms).\n\nThis repo contains the GGUF format model files for [INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0](https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0).\n\n## Quick Start using Python\n\nInstall the required package:\n```bash\npip install llama-cpp-python\n```\n\nExample chat completion:\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(\n model_path=\"path/to/your/model.gguf\",\n n_ctx=8192,\n penalize_nl=False\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"Кога е основан Софийският университет?\"}]\nresponse = llm.create_chat_completion(\n messages=messages,\n max_tokens=2048, # Choose maximum generated tokens\n temperature=0.1,\n top_p=0.9,\n repeat_penalty=1.0,\n stop=[\"<eos>\", \"<end_of_turn>\"]\n)\n\n\n```\n\nExample normal completion:\n\n```python\nfrom llama_cpp import Llama\n\nllm = Llama(\n model_path=\"path/to/your/model.gguf\",\n n_ctx=8192,\n penalize_nl=False\n)\n\nprompt = \"<start_of_turn>user\\nКога е основан Софийският университет?<end_of_turn>\\n<start_of_turn>model\\n\"\nresponse = llm(\n prompt,\n max_tokens=2048, # Choose maximum generated tokens\n temperature=0.1,\n top_p=0.9,\n repeat_penalty=1.0,\n stop=[\"<eos>\",\"<end_of_turn>\"]\n)\n```",
"related_quantizations": []
},
"tags": [
"gguf",
"license:gemma",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 5,
"downloads": 469,
"gated": false,
"private": false,
"last_modified": "2024-11-19T08:21:47.000Z",
"created_at": "2024-11-16T06:52:44.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6738413c98b2d09abc9366cf",
"id": "INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0-GGUF",
"modelId": "INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0-GGUF",
"sha": "983a96df1629b7f7b8cdad47124529e38651e46c",
"createdAt": "2024-11-16T06:52:44.000Z",
"lastModified": "2024-11-19T08:21:47.000Z",
"author": "INSAIT-Institute",
"downloads": 469,
"likes": 5,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 12
}